Augmented design automation: Leveraging parametric designs using large language models
Publikation: Beiträge in Zeitschriften › Konferenzaufsätze in Fachzeitschriften › Forschung › begutachtet
Standard
in: Proceedings of the Design Society, Jahrgang 5, 01.08.2025, S. 671-680.
Publikation: Beiträge in Zeitschriften › Konferenzaufsätze in Fachzeitschriften › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Augmented design automation
T2 - 25th International Conference on Engineering Design, ICED 2025
AU - Schöfer, Fabian
AU - Seibel, Arthur
N1 - Publisher Copyright: © The Author(s) 2025.
PY - 2025/8/1
Y1 - 2025/8/1
N2 - Traditional design automation enables parameterized customization but struggles with adapting to abstract or context-based user requirements. Recent advances in integrating large language models with script-driven CAD kernels provide a novel framework for context-sensitive, natural-language-driven design processes. Here, we present augmented design automation, enhancing parametric workflows with a semantic layer to interpret and execute functional, constructional, and effective user requests. Using CadQuery, experiments on a sandal model demonstrate the system's capability to generate diverse and meaningful design variations from abstract prompts. This approach overcomes traditional limitations, enabling flexible and user-centric product development. Future research should focus on addressing complex assemblies and exploring generative design capabilities to expand the potential of this approach.
AB - Traditional design automation enables parameterized customization but struggles with adapting to abstract or context-based user requirements. Recent advances in integrating large language models with script-driven CAD kernels provide a novel framework for context-sensitive, natural-language-driven design processes. Here, we present augmented design automation, enhancing parametric workflows with a semantic layer to interpret and execute functional, constructional, and effective user requests. Using CadQuery, experiments on a sandal model demonstrate the system's capability to generate diverse and meaningful design variations from abstract prompts. This approach overcomes traditional limitations, enabling flexible and user-centric product development. Future research should focus on addressing complex assemblies and exploring generative design capabilities to expand the potential of this approach.
KW - computer aided design (CAD)
KW - design automation
KW - large language models
KW - machine learning
KW - user centred design
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=105022853569&partnerID=8YFLogxK
U2 - 10.1017/pds.2025.10081
DO - 10.1017/pds.2025.10081
M3 - Conference article in journal
AN - SCOPUS:105022853569
VL - 5
SP - 671
EP - 680
JO - Proceedings of the Design Society
JF - Proceedings of the Design Society
SN - 2732-527X
Y2 - 11 August 2025 through 14 August 2025
ER -